{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DNJGR3PLJ7VCDKZEWBE6Q4WZHP","short_pith_number":"pith:DNJGR3PL","schema_version":"1.0","canonical_sha256":"1b5268edeb4fea21ab24b049e872d93bea4f27085f33a347a600b2066938cb53","source":{"kind":"arxiv","id":"2204.03475","version":2},"attestation_state":"computed","paper":{"title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Asaf Noy, Emanuel Ben-Baruch, Hussam Lawen, Tal Ridnik","submitted_at":"2022-04-07T14:43:58Z","abstract_excerpt":"ImageNet serves as the primary dataset for evaluating the quality of computer-vision models. The common practice today is training each architecture with a tailor-made scheme, designed and tuned by an expert. In this paper, we present a unified scheme for training any backbone on ImageNet. The scheme, named USI (Unified Scheme for ImageNet), is based on knowledge distillation and modern tricks. It requires no adjustments or hyper-parameters tuning between different models, and is efficient in terms of training times. We test USI on a wide variety of architectures, including CNNs, Transformers,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.03475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T14:43:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d576eef10f64e2f2944f19374ecabda30b09000e2b46ae62d91ac2567457837e","abstract_canon_sha256":"07e7c51d6f06a4090989433c9ca5b534768a0881db2b56f8134f9eb9d5412d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:40.933609Z","signature_b64":"ahY9VZxRKKZufFD1Xmv4sOrsfvfREomvsKl2W31UwYCmI4LOROC2o6w9YYMAsQSK7KiP+17qe2gwpNErueKuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b5268edeb4fea21ab24b049e872d93bea4f27085f33a347a600b2066938cb53","last_reissued_at":"2026-07-05T04:22:40.933193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:40.933193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving ImageNet: a Unified Scheme for Training any Backbone to Top Results","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Asaf Noy, Emanuel Ben-Baruch, Hussam Lawen, Tal Ridnik","submitted_at":"2022-04-07T14:43:58Z","abstract_excerpt":"ImageNet serves as the primary dataset for evaluating the quality of computer-vision models. The common practice today is training each architecture with a tailor-made scheme, designed and tuned by an expert. In this paper, we present a unified scheme for training any backbone on ImageNet. The scheme, named USI (Unified Scheme for ImageNet), is based on knowledge distillation and modern tricks. It requires no adjustments or hyper-parameters tuning between different models, and is efficient in terms of training times. We test USI on a wide variety of architectures, including CNNs, Transformers,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03475","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.03475/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.03475","created_at":"2026-07-05T04:22:40.933254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03475v2","created_at":"2026-07-05T04:22:40.933254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03475","created_at":"2026-07-05T04:22:40.933254+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNJGR3PLJ7VC","created_at":"2026-07-05T04:22:40.933254+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNJGR3PLJ7VCDKZE","created_at":"2026-07-05T04:22:40.933254+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNJGR3PL","created_at":"2026-07-05T04:22:40.933254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP","json":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP.json","graph_json":"https://pith.science/api/pith-number/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/graph.json","events_json":"https://pith.science/api/pith-number/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/events.json","paper":"https://pith.science/paper/DNJGR3PL"},"agent_actions":{"view_html":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP","download_json":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP.json","view_paper":"https://pith.science/paper/DNJGR3PL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03475&json=true","fetch_graph":"https://pith.science/api/pith-number/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/graph.json","fetch_events":"https://pith.science/api/pith-number/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/action/storage_attestation","attest_author":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/action/author_attestation","sign_citation":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/action/citation_signature","submit_replication":"https://pith.science/pith/DNJGR3PLJ7VCDKZEWBE6Q4WZHP/action/replication_record"}},"created_at":"2026-07-05T04:22:40.933254+00:00","updated_at":"2026-07-05T04:22:40.933254+00:00"}